From 41477acf092251eb0cfe83068f48dbcb2521478a Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 7 Jun 2018 14:19:54 -0300 Subject: perf hists: Save the callchain_size in struct hist_entry So that we can figure out the real size of the struct and also be able to tell if callchains may be present in this histogram entry. Since we can't always guarantee that from hist_entry->hists we can use hists_to_evsel, to then look at evsel->attr.sample_type for PERF_SAMPLE_CALLCHAIN, like with the 'perf c2c' tool, that uses plain 'struct hists' instances, we need another way of deciding if a specific hist_entry instance has callchains associated with it, i.e. if its hist_entry->callchain[0] has space allocated for. Cc: Adrian Hunter Cc: David Ahern Cc: Jin Yao Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-ptvndealxs1k7myluvu9flnq@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/hist.c | 6 ++++-- tools/perf/util/sort.h | 2 ++ 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 52e8fda93a47..0441a92b855f 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -370,9 +370,11 @@ void hists__delete_entries(struct hists *hists) static int hist_entry__init(struct hist_entry *he, struct hist_entry *template, - bool sample_self) + bool sample_self, + size_t callchain_size) { *he = *template; + he->callchain_size = callchain_size; if (symbol_conf.cumulate_callchain) { he->stat_acc = malloc(sizeof(he->stat)); @@ -473,7 +475,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template, he = ops->new(callchain_size); if (he) { - err = hist_entry__init(he, template, sample_self); + err = hist_entry__init(he, template, sample_self, callchain_size); if (err) { ops->free(he); he = NULL; diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 7cf2d5cc038e..9ab9257ed887 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -112,6 +112,8 @@ struct hist_entry { char level; u8 filtered; + + u16 callchain_size; union { /* * Since perf diff only supports the stdio output, TUI -- cgit v1.2.3 From e5654455795f2f89328f7b301dacb6926e57e2b8 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 7 Jun 2018 14:27:19 -0300 Subject: perf hists: Make hist_entry__has_callchains() work with 'perf c2c' Since 'perf c2c' uses 'struct hists' not allocated together with a 'struct perf_evsel' instance, we can't go from a 'struct hist_entry' pointer to a 'struct perf_evsel' via he->hists, so, instead, check if space was set aside for hist_entry->callchain[0] at hist_entry__new() time. Reported-by: Jin Yao Reported-by: Jiri Olsa Cc: Adrian Hunter Cc: David Ahern Cc: Namhyung Kim Cc: Wang Nan Fixes: fabd37b837f6 ("perf hists: Check if a hist_entry has callchains before using them") Link: https://lkml.kernel.org/n/tip-e8ife8djvvvwmeze3s4yodii@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/sort.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 9ab9257ed887..8bf302cafcec 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -155,7 +155,7 @@ struct hist_entry { static __pure inline bool hist_entry__has_callchains(struct hist_entry *he) { - return hists__has_callchains(he->hists); + return he->callchain_size != 0; } static inline bool hist_entry__has_pairs(struct hist_entry *he) -- cgit v1.2.3 From 29f9fcdd3f8edccad5809cf939ce921752460fe7 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 7 Jun 2018 14:33:31 -0300 Subject: perf hists browser gtk: Use hist_entry__has_callchains() Since we can't go from struct hists to struct evsel for all cases (c2c is an exception) and we have access to the hist_entry, use hist_entry__has_callchains() in the GTK+ hists browser to figure out if callchains are available. Cc: Adrian Hunter Cc: David Ahern Cc: Jin Yao Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-8owkgrruzzi5emvblwh4e6le@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/gtk/hists.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index b085f1b3e34d..4ab663ec3e5e 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -382,7 +382,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, gtk_tree_store_set(store, &iter, col_idx++, s, -1); } - if (hists__has_callchains(hists) && + if (hist_entry__has_callchains(h) && symbol_conf.use_callchain && hists__has(hists, sym)) { if (callchain_param.mode == CHAIN_GRAPH_REL) total = symbol_conf.cumulate_callchain ? -- cgit v1.2.3 From c9d366287042489090da0391318df528bdce9941 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 7 Jun 2018 14:42:27 -0300 Subject: perf hists: Reimplement hists__has_callchains() There are places where we have only access to struct hists and need to know if any of its hist_entries has callchains, like when drawing headers for the various output modes (stdio, TUI, etc), so, when adding a new hist_entry, check if it has callchains, storing this info for later use by hists__has_callchains(). This reimplementation is necessary because not always a 'struct hists' is allocated together with a 'struct perf evsel', so we can't go from 'hists' to 'perf_event_attr.sample_type & PERF_SAMPLE_CALLCHAIN'. Cc: Adrian Hunter Cc: David Ahern Cc: Jin Yao Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: https://lkml.kernel.org/n/tip-hg5g7yddjio3ljwyqnnaj5dt@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/hist.c | 6 ++++-- tools/perf/util/hist.h | 4 ++-- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 0441a92b855f..828cb9794c76 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -621,9 +621,11 @@ __hists__add_entry(struct hists *hists, .raw_data = sample->raw_data, .raw_size = sample->raw_size, .ops = ops, - }; + }, *he = hists__findnew_entry(hists, &entry, al, sample_self); - return hists__findnew_entry(hists, &entry, al, sample_self); + if (!hists->has_callchains && he && he->callchain_size != 0) + hists->has_callchains = true; + return he; } struct hist_entry *hists__add_entry(struct hists *hists, diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 06607c434949..73049f7f0f60 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -85,6 +85,7 @@ struct hists { struct events_stats stats; u64 event_stream; u16 col_len[HISTC_NR_COLS]; + bool has_callchains; int socket_filter; struct perf_hpp_list *hpp_list; struct list_head hpp_formats; @@ -222,8 +223,7 @@ static inline struct hists *evsel__hists(struct perf_evsel *evsel) static __pure inline bool hists__has_callchains(struct hists *hists) { - const struct perf_evsel *evsel = hists_to_evsel(hists); - return evsel__has_callchain(evsel); + return hists->has_callchains; } int hists__init(void); -- cgit v1.2.3 From f7fa827f5f432a0b1f34e10fc49da93aeef9f817 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 7 Jun 2018 00:15:05 +0200 Subject: perf tools: Fix error index for pmu event parser For events we provide specific error message we need to set error column index, PMU parser is missing that, adding it. Before: $ perf stat -e cycles,krava/cycles/ kill event syntax error: 'cycles,krava/cycles/' \___ Cannot find PMU `krava'. Missing kernel support? After: $ perf stat -e cycles,krava/cycles/ kill event syntax error: 'cycles,krava/cycles/' \___ Cannot find PMU `krava'. Missing kernel support? Signed-off-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Milian Wolff Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/20180606221513.11302-3-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.y | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 155d2570274f..da8fe57691b8 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -227,11 +227,16 @@ event_def: event_pmu | event_pmu: PE_NAME opt_pmu_config { + struct parse_events_state *parse_state = _parse_state; + struct parse_events_error *error = parse_state->error; struct list_head *list, *orig_terms, *terms; if (parse_events_copy_term_list($2, &orig_terms)) YYABORT; + if (error) + error->idx = @1.first_column; + ALLOC_LIST(list); if (parse_events_add_pmu(_parse_state, list, $1, $2, false, false)) { struct perf_pmu *pmu = NULL; -- cgit v1.2.3 From 9660e08ee8cbc94ac835f2c30576c6e51fbece8f Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 7 Jun 2018 00:15:06 +0200 Subject: perf stat: Add --interval-clear option Adding --interval-clear option to clear the screen before next interval. Committer testing: # perf stat -I 1000 --interval-clear And, as expected, it behaves almost like: # watch -n 0 perf stat -a sleep 1 Signed-off-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Milian Wolff Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/20180606221513.11302-4-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-stat.txt | 3 +++ tools/perf/builtin-stat.c | 11 +++++++++-- 2 files changed, 12 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 5dfe102fb5b5..b10a90b6a718 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -178,6 +178,9 @@ Print count deltas for fixed number of times. This option should be used together with "-I" option. example: 'perf stat -I 1000 --interval-count 2 -e cycles -a' +--interval-clear:: +Clear the screen before next interval. + --timeout msecs:: Stop the 'perf stat' session and print count deltas after N milliseconds (minimum: 10 ms). This option is not supported with the "-I" option. diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 096ccb25c11f..f1532e3ac7d7 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -65,6 +65,7 @@ #include "util/tool.h" #include "util/string2.h" #include "util/metricgroup.h" +#include "util/top.h" #include "asm/bug.h" #include @@ -173,6 +174,7 @@ static struct cpu_map *aggr_map; static aggr_get_id_t aggr_get_id; static bool append_file; static bool interval_count; +static bool interval_clear; static const char *output_name; static int output_fd; static int print_free_counters_hint; @@ -1704,9 +1706,12 @@ static void print_interval(char *prefix, struct timespec *ts) FILE *output = stat_config.output; static int num_print_interval; + if (interval_clear) + puts(CONSOLE_CLEAR); + sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep); - if (num_print_interval == 0 && !csv_output) { + if ((num_print_interval == 0 && !csv_output) || interval_clear) { switch (stat_config.aggr_mode) { case AGGR_SOCKET: fprintf(output, "# time socket cpus"); @@ -1738,7 +1743,7 @@ static void print_interval(char *prefix, struct timespec *ts) } } - if (num_print_interval == 0 && metric_only) + if ((num_print_interval == 0 && metric_only) || interval_clear) print_metric_headers(" ", true); if (++num_print_interval == 25) num_print_interval = 0; @@ -2057,6 +2062,8 @@ static const struct option stat_options[] = { "(overhead is possible for values <= 100ms)"), OPT_INTEGER(0, "interval-count", &stat_config.times, "print counts for fixed number of times"), + OPT_BOOLEAN(0, "interval-clear", &interval_clear, + "clear screen in between new interval"), OPT_UINTEGER(0, "timeout", &stat_config.timeout, "stop workload and print counts after a timeout period in ms (>= 10ms)"), OPT_SET_UINT(0, "per-socket", &stat_config.aggr_mode, -- cgit v1.2.3 From b37d33edbf41b532ddd156707c037c6f4784e40b Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 7 Jun 2018 00:15:07 +0200 Subject: perf stat: Use only color_fprintf call in print_metric_only We can call color_fprintf also for non color case, it's handled properly. This change simplifies following patch. Signed-off-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Milian Wolff Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/20180606221513.11302-5-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index f1532e3ac7d7..9e7b6f108956 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1008,10 +1008,7 @@ static void print_metric_only(void *ctx, const char *color, const char *fmt, if (!valid_only_metric(unit)) return; unit = fixunit(buf, os->evsel, unit); - if (color) - n = color_fprintf(out, color, fmt, val); - else - n = fprintf(out, fmt, val); + n = color_fprintf(out, color ?: "", fmt, val); if (n > METRIC_ONLY_LEN) n = METRIC_ONLY_LEN; if (mlen < strlen(unit)) -- cgit v1.2.3 From f515572734fb323aa0efe9ea2c546cd7fee327f7 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 7 Jun 2018 00:15:08 +0200 Subject: perf stat: Fix metric column header display alignment Make the metric only display aligned. Before: # perf stat --topdown -I 1000 # time core cpus retiring bad speculation frontend bound backend bound 1.000394323 S0-C0 2 37.4% 12.0% 31.4% 19.2% 1.000394323 S0-C1 2 25.1% 9.2% 43.8% 21.9% 2.001521204 S0-C0 2 36.4% 11.4% 32.4% 19.8% 2.001521204 S0-C1 2 26.2% 9.4% 43.1% 21.3% 3.001930208 S0-C0 2 35.1% 10.7% 33.6% 20.6% 3.001930208 S0-C1 2 28.9% 10.0% 40.0% 21.1% After: # perf stat --topdown -I 1000 # time core cpus retiring bad speculation frontend bound backend bound 1.000303722 S0-C0 2 34.2% 7.6% 34.2% 24.0% 1.000303722 S0-C1 2 33.1% 6.4% 36.9% 23.6% 2.001281055 S0-C0 2 34.6% 6.7% 36.8% 21.8% 2.001281055 S0-C1 2 32.8% 7.1% 38.1% 22.0% 3.001546080 S0-C0 2 39.3% 5.5% 32.7% 22.5% 3.001546080 S0-C1 2 37.8% 6.0% 33.1% 23.1% Signed-off-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Milian Wolff Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/20180606221513.11302-6-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 9e7b6f108956..8f3fdc052728 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1001,19 +1001,20 @@ static void print_metric_only(void *ctx, const char *color, const char *fmt, { struct outstate *os = ctx; FILE *out = os->fh; - int n; - char buf[1024]; + char buf[1024], str[1024]; unsigned mlen = METRIC_ONLY_LEN; if (!valid_only_metric(unit)) return; unit = fixunit(buf, os->evsel, unit); - n = color_fprintf(out, color ?: "", fmt, val); - if (n > METRIC_ONLY_LEN) - n = METRIC_ONLY_LEN; if (mlen < strlen(unit)) mlen = strlen(unit) + 1; - fprintf(out, "%*s", mlen - n, ""); + + if (color) + mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1; + + color_snprintf(str, sizeof(str), color ?: "", fmt, val); + fprintf(out, "%*s ", mlen, str); } static void print_metric_only_csv(void *ctx, const char *color __maybe_unused, @@ -1053,7 +1054,7 @@ static void print_metric_header(void *ctx, const char *color __maybe_unused, if (csv_output) fprintf(os->fh, "%s%s", unit, csv_sep); else - fprintf(os->fh, "%-*s ", METRIC_ONLY_LEN, unit); + fprintf(os->fh, "%*s ", METRIC_ONLY_LEN, unit); } static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg) @@ -1721,7 +1722,7 @@ static void print_interval(char *prefix, struct timespec *ts) fprintf(output, " counts %*s events\n", unit_width, "unit"); break; case AGGR_NONE: - fprintf(output, "# time CPU"); + fprintf(output, "# time CPU "); if (!metric_only) fprintf(output, " counts %*s events\n", unit_width, "unit"); break; -- cgit v1.2.3 From c1a1f5d9da800dc715d8c1d8a9692c63c70c2955 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 7 Jun 2018 00:15:09 +0200 Subject: perf stat: Allow to specify specific metric column len The following change will introduce new metrics, that doesn't need such wide hard coded spacing. Switch METRIC_ONLY_LEN macro usage with metric_only_len variable. Signed-off-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Milian Wolff Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/20180606221513.11302-7-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 8f3fdc052728..3fc1f5286d50 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -145,6 +145,8 @@ static struct target target = { typedef int (*aggr_get_id_t)(struct cpu_map *m, int cpu); +#define METRIC_ONLY_LEN 20 + static int run_count = 1; static bool no_inherit = false; static volatile pid_t child_pid = -1; @@ -182,6 +184,7 @@ static int print_mixed_hw_group_error; static u64 *walltime_run; static bool ru_display = false; static struct rusage ru_data; +static unsigned int metric_only_len = METRIC_ONLY_LEN; struct perf_stat { bool record; @@ -969,8 +972,6 @@ static void print_metric_csv(void *ctx, fprintf(out, "%s%s%s%s", csv_sep, vals, csv_sep, unit); } -#define METRIC_ONLY_LEN 20 - /* Filter out some columns that don't work well in metrics only mode */ static bool valid_only_metric(const char *unit) @@ -1002,7 +1003,7 @@ static void print_metric_only(void *ctx, const char *color, const char *fmt, struct outstate *os = ctx; FILE *out = os->fh; char buf[1024], str[1024]; - unsigned mlen = METRIC_ONLY_LEN; + unsigned mlen = metric_only_len; if (!valid_only_metric(unit)) return; @@ -1054,7 +1055,7 @@ static void print_metric_header(void *ctx, const char *color __maybe_unused, if (csv_output) fprintf(os->fh, "%s%s", unit, csv_sep); else - fprintf(os->fh, "%*s ", METRIC_ONLY_LEN, unit); + fprintf(os->fh, "%*s ", metric_only_len, unit); } static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg) -- cgit v1.2.3 From a5cfa6217c94a1f1cfad4481fc14f5fc399abde3 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 7 Jun 2018 00:15:10 +0200 Subject: perf stat: Add event parsing error handling to add_default_attributes Add missing error handling for parse_events calls in add_default_attributes functions. The error handler displays error details, like for transactions (-T): Before: $ perf stat -T Cannot set up transaction events After: $ perf stat -T Cannot set up transaction events event syntax error: '..cycles,cpu/cycles-t/,cpu/tx-start/,cpu/el-start/,cpu/cycles-ct/}' \___ unknown term Signed-off-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Milian Wolff Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/20180606221513.11302-8-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 3fc1f5286d50..22547a490e1f 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -2442,14 +2442,13 @@ static int add_default_attributes(void) (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) }, }; + struct parse_events_error errinfo; /* Set attrs if no event is selected and !null_run: */ if (null_run) return 0; if (transaction_run) { - struct parse_events_error errinfo; - if (pmu_have_event("cpu", "cycles-ct") && pmu_have_event("cpu", "el-start")) err = parse_events(evsel_list, transaction_attrs, @@ -2460,6 +2459,7 @@ static int add_default_attributes(void) &errinfo); if (err) { fprintf(stderr, "Cannot set up transaction events\n"); + parse_events_print_error(&errinfo, transaction_attrs); return -1; } return 0; @@ -2485,10 +2485,11 @@ static int add_default_attributes(void) pmu_have_event("msr", "smi")) { if (!force_metric_only) metric_only = true; - err = parse_events(evsel_list, smi_cost_attrs, NULL); + err = parse_events(evsel_list, smi_cost_attrs, &errinfo); } else { fprintf(stderr, "To measure SMI cost, it needs " "msr/aperf/, msr/smi/ and cpu/cycles/ support\n"); + parse_events_print_error(&errinfo, smi_cost_attrs); return -1; } if (err) { @@ -2523,12 +2524,13 @@ static int add_default_attributes(void) if (topdown_attrs[0] && str) { if (warn) arch_topdown_group_warn(); - err = parse_events(evsel_list, str, NULL); + err = parse_events(evsel_list, str, &errinfo); if (err) { fprintf(stderr, "Cannot set up top down events %s: %d\n", str, err); free(str); + parse_events_print_error(&errinfo, str); return -1; } } else { -- cgit v1.2.3 From 4c8205273626f27b9e5a64bdc194ab483a8cce66 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 8 Jun 2018 02:22:11 +0200 Subject: perf c2c: Keep struct hist_entry at the end of struct c2c_hist_entry Exactly as the comment just before 'struct c2c_hist_entry" says, i.e. the last entry in struct hist_entry is a zero length array, that when allocating space for hist_entry gets extra space if callchains are in use, which, if hist_entry is not at the end of c2c_hist_entry, the members after it gets corrupted when callchains get added to the rb trees collecting them, etc. Signed-off-by: Jiri Olsa Reported-by: Arnaldo Carvalho de Melo Cc: Jin Yao Fixes: 7f834c2e84bb ("perf c2c report: Display node for cacheline address") Link: http://lkml.kernel.org/n/tip-bh0ke4fh2ygpj3yowna7o1di@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-c2c.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'tools') diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index 307b3594525f..6a8738f7ead3 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -56,16 +56,16 @@ struct c2c_hist_entry { struct compute_stats cstats; + unsigned long paddr; + unsigned long paddr_cnt; + bool paddr_zero; + char *nodestr; + /* * must be at the end, * because of its callchain dynamic entry */ struct hist_entry he; - - unsigned long paddr; - unsigned long paddr_cnt; - bool paddr_zero; - char *nodestr; }; static char const *coalesce_default = "pid,iaddr"; -- cgit v1.2.3 From fad76d4333fe73cf3f73704aa34d4ce523b1c458 Mon Sep 17 00:00:00 2001 From: Seeteena Thoufeek Date: Fri, 8 Jun 2018 16:32:28 +0530 Subject: perf script: Show hw-cache events 'perf script' fails to report hardware cache events (PERF_TYPE_HW_CACHE) where as 'perf report' shows the samples. Fix it. Ex, # perf record -e L1-dcache-loads ./a.out [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.008 MB perf.data (11 samples)] Before patch: # perf script | wc -l 0 After patch: # perf script | wc -l 11 Committer testing: [root@jouet ~]# perf script | head -30 | tail Timer 9803 [2] 8.963330: 1554 L1-dcache-loads: 7ffef89baae4 __vdso_clock_gettime+0xf4 ([vdso]) swapper 0 [2] 8.963343: 5626 L1-dcache-loads: ffffffffa66f4f6b cpuidle_not_av+0xb (/lib/modules/4.17.0-rc5/build/vmlinux) firefox 4853 [2] 8.964070: 18935 L1-dcache-loads: 7f0b9a00dc30 xcb_poll_for_event+0x0 (/usr/lib64/libxcb.so.1.1.0) Softwar~cTh 4928 [2] 8.964548: 15928 L1-dcache-loads: ffffffffa60d795c update_curr+0x10c (/lib/modules/4.17.0-rc5/build/vmlinux) firefox 4853 [2] 8.964675: 14978 L1-dcache-loads: ffffffffa6897018 mutex_unlock+0x18 (/lib/modules/4.17.0-rc5/build/vmlinux) gnome-shell 2026 [3] 8.964693: 50670 L1-dcache-loads: 7fa08854de6d g_source_iter_next+0x6d (/usr/lib64/libglib-2.0.so.0.5400.3) Compositor 4929 [1] 8.964784: 71772 L1-dcache-loads: 7f0b936bf078 [unknown] (/usr/lib64/firefox/libxul.so) Xwayland 2096 [2] 8.964919: 16799 L1-dcache-loads: 7f68ce2fcb8a glXGetCurrentContext+0x1a (/usr/lib64/libGLX.so.0.0.0) gnome-shell 2026 [3] 8.964997: 50670 L1-dcache-loads: 7fa08854de6d g_source_iter_next+0x6d (/usr/lib64/libglib-2.0.so.0.5400.3) [root@jouet ~]# Signed-off-by: Seeteena Thoufeek Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1528455748-20087-1-git-send-email-s1seetee@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'tools') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index b3bf35512d21..a31d7082188e 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -180,6 +180,18 @@ static struct { PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE }, + [PERF_TYPE_HW_CACHE] = { + .user_set = false, + + .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | + PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | + PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | + PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | + PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD, + + .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, + }, + [PERF_TYPE_RAW] = { .user_set = false, -- cgit v1.2.3